Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation used in code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Variable assignment or initialization

    np_acts-logits-general · gemini-2.0-flash

    assignment to null or false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Britannique
    -0.70
    THISDAY
    -0.58
    PostInfinity
    -0.50
     into
    -0.48
     ranks
    -0.48
    ");
    -0.47
    leştir
    -0.47
    ";
    -0.47
    "));
    -0.47
    ');
    -0.47
    POSITIVE LOGITS
     None
    0.81
     null
    0.80
    None
    0.74
     nowhere
    0.69
     default
    0.68
    CloseOperation
    0.67
    intios
    0.67
    //
    0.65
    default
    0.63
     NULL
    0.62
    Act Density 0.083%

    No Known Activations